|
|
| from transformers import PretrainedConfig, PreTrainedModel |
| import json |
|
|
| class Idefics2VisionConfig(PretrainedConfig): |
| model_type = "Idefics2VisionConfig" |
|
|
| def __init__( |
| self, |
| hidden_size=768, |
| intermediate_size=3072, |
| num_hidden_layers=12, |
| num_attention_heads=12, |
| num_channels=3, |
| image_size=224, |
| patch_size=32, |
| hidden_act="gelu_pytorch_tanh", |
| layer_norm_eps=1e-6, |
| attention_dropout=0.0, |
| initializer_range=0.02, |
| model_type='Idefics2VisionConfig', |
| **kwargs, |
| ): |
|
|
| self.hidden_size = hidden_size |
| self.intermediate_size = intermediate_size |
| self.num_hidden_layers = num_hidden_layers |
| self.num_attention_heads = num_attention_heads |
| self.num_channels = num_channels |
| self.patch_size = patch_size |
| self.image_size = image_size |
| self.attention_dropout = attention_dropout |
| self.layer_norm_eps = layer_norm_eps |
| self.hidden_act = hidden_act |
| self.initializer_range = initializer_range |
| |
| super().__init__(**kwargs) |
|
|
|
|
